divisible-work
claudeVerified GPT-6.1 Sol or GPT-6 Luna work, preferring permitted Codex chats with native subagent fallback and durable task state.
1 skill
2
claude
adversarial-review
Two independent adversarial approvals for a digest-checked task result.
/
Plugin adversarial-review from marketplace emlembow-skills in Emlembow/skills. Commands read from the repo's manifest — 1 month ago.
What it installs
Skills (1)
adversarial-reviewRun a file-audited completion loop that requires two consecutive fresh-context subagents to independently try to disprove the same versioned, digest-checked task result. Use when the user invokes $adversarial-review, asks for two independent adversarial approvals, or requires a result to survive rep
More from Emlembow/skills
All 3 plugins →research-loop
claudeMetric-driven experiments with holdouts, immutable evidence, and replay-safe recovery.
1 skill
2
Maintain adversarial-review?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.
claude & codex plugins3 plugins